{ "architectures": [ "AsmEncoder" ], "auto_map": { "AutoModel": "optrans_modeling.AsmEncoder" }, "attention_probs_dropout_prob": 0.1, "bla_dim": 1024, "embedding_size": 768, "hidden_act": "gelu", "hidden_dropout_prob": 0.1, "hidden_size": 768, "initializer_range": 0.02, "intermediate_size": 3072, "layer_norm_eps": 1e-12, "max_position_embeddings": 2048, "model_type": "roformer", "num_attention_heads": 12, "num_hidden_layers": 12, "pad_token_id": 1, "rotary_value": false, "token_type_ids": "share", "torch_dtype": "bfloat16", "transformers_version": "4.35.0", "type_vocab_size": 2, "use_bias": false, "use_cache": true, "vocab_size": 33494 }